No full-text available
To read the full-text of this research,
you can request a copy directly from the authors.
Agent-based intelligent system development for decision support in chemical process industry
Abstract
This paper presents an agent-based intelligent system to support coordinate manufacturing execution and decision-making in chemical process industry. A multi-agent system (MAS) framework is developed to provide a flexible infrastructure for the integration of chemical process information and process models. The system comprise of a process knowledge base and a group of functional agents. Agents in the system can communicate and cooperate with each other to exchange and share information, and to achieve timely decisions in dealing with various scenarios in process operations and manufacturing management. Process simulation, artificial intelligent technique, rule-based decision supports are integrated in this system for process analysis, process monitoring, process performance prediction and operation suggestion. The implementation of this agent-based system was illustrated with two case studies, including one application in process monitoring and process performance prediction for a chemical process and one application in de-bottlenecking of a site utility system.
... En la gura 4.1 se puede observar que en el enfoque planteado por Gao et al. (2009), se sugiere una arquitectura donde se disponga tres tipos de agentes inteligentes: agentes usuarios, que reciben requerimientos de los usuarios y despliegan resultados; agentes intermediarios, responsables por la descomposición y coordinación de la ejecución de cada una de las tareas requeridas para satisfacer el requerimiento del usuario; y agentes de tareas que ejecutan actividades especícas asignadas por el agente intermediario. Es importante hacer notar que entre los agentes de tareas descritos en el trabajo de Gao et al. (2009) destacan los requeridos para llevar a cabo cálculos de optimización y programación, tal como corresponde al agente propuesto en este trabajo de tesis. ...
... En el primero de ellos se destaca la posibilidad de que los agentes traten con recursos de información diversos y heterogéneos, incorporen codigos heredados (legacy) encapsulados y funcionen en un ambiente de red distribuida. Además, se hace énfasis en la posibilidad de contar con una plataforma más fácil de mantener y escalar (Gao et al. , 2009). En el segundo punto de vista se muestran resultados concretos respecto de la superioridad de sistemas basados en agentes para ejecutar tareas de control y optimización de procesos (Ramírez et al. , 2009;Gaoa et al. , 2006). ...
... Sin embargo, la mayoría de los recursos de información técnica y operacional de sistemas de ingeniería química residen en formato electrónico, en un ambiente de red donde, no obstante, no se comunican todos los diferentes elementos que componen dicha red. La mayoría de los productos de software utilizados para solucionar problemas operacionales o de diseño de ingeniería no son capaces de comunicarse entre sí lo que hace cuesta arriba la posibilidad de que estos programas puedan mantener algún tipo de cooperación(Gao et al. , 2009).En el trabajo desarrollado porGao et al. (2009) se parte de las premisas descritas en el párrafo anterior para proponer una arquitectura basada en agentes inteligentes que permita integrar la información distribuida en repositorios electrónicos y los distintos software utilizados para simulación y soporte a las decisiones basado en reglas, con el objeto de contar con una manufactura colaborativa que permita ejecutar de una forma más eciente tareas de análisis, monitorización y predicción del desempeño de procesos. ...
... kP.q/k 1 < 1 if there exist positive-definite matrices P 0 and P j 0 (j D 1, 2, : : : , max 1) and gain matricesˆ, ‰ and satisfying 2 By setting Q D P 1 and Q j D P 1 P j P 1 , j D 1, 2, : : : , max 1, pre-multiplying and post-multiplying the aforementioned inequality by diag¹P 1 , I , P 1 , P 1 , : : : , P 1 , I º, and using block-row-column exchanges, we can equivalently obtain the LMI (38). That is, kP.q/k 1 < 1 holds under (38), which hence guarantees kI Hk 2 < 1 on the basis of the properties of block Toeplitz matrices [48] (see also the proof of Theorem 1). ...
... kP.q/k 1 < 1 if there exist positive-definite matrices P 0 and P j 0 (j D 1, 2, : : : , max 1) and gain matricesˆ, ‰ and satisfying 2 By setting Q D P 1 and Q j D P 1 P j P 1 , j D 1, 2, : : : , max 1, pre-multiplying and post-multiplying the aforementioned inequality by diag¹P 1 , I , P 1 , P 1 , : : : , P 1 , I º, and using block-row-column exchanges, we can equivalently obtain the LMI (38). That is, kP.q/k 1 < 1 holds under (38), which hence guarantees kI Hk 2 < 1 on the basis of the properties of block Toeplitz matrices [48] (see also the proof of Theorem 1). By noticing this fact, we take the Euclidean norm on both sides of (36), and then we can conclude that the formation objective (3) holds with lim k!1 kE k k 2 D 0 being achieved monotonically. ...
This paper deals with formation control problems for multi-agent systems by using iterative learning control (ILC) design approaches. Distributed formation ILC algorithms are presented to enable all agents in directed graphs to achieve the desired relative formations perfectly over a finite-time interval. It is shown that not only asymptotic stability but also monotonic convergence of multi-agent formation ILC can be accomplished, and the convergence conditions in terms of linear matrix inequalities can be simultaneously established. The derived results are also applicable to multi-agent systems that are subject to stochastic disturbances and model uncertainties. Furthermore, the feasibility of convergence conditions and the effect of communication delays are discussed for the proposed multi-agent formation ILC algorithms. Simulation results are given for uncertain multi-agent systems to verify the theoretical study. Copyright © 2012 John Wiley & Sons, Ltd.
... Initial approaches in agent based systems utilized rulebased agents for tasks such as intrusion detection (Jha and Hassan (2002)) or decision support (Gao et al. (2009)). Despite some success, rule-based agents are inherently limited to predefined situations, making them less adaptable to novel scenarios (Siu et al. (2021)). ...
As chemical plants evolve towards full autonomy, the need for effective fault handling and control in dynamic, unpredictable environments becomes increasingly critical. This paper proposes an innovative approach to industrial automation, introducing validation and reprompting architectures utilizing large language model (LLM)-based autonomous control agents. The proposed agentic system, comprising of operator, validator, and reprompter agents, enables autonomous management of control tasks, adapting to unforeseen disturbances without human intervention. By utilizing validation and reprompting architectures, the framework allows agents to recover from errors and continuously improve decision-making in real-time industrial scenarios. We hypothesize that this mechanism will enhance performance and reliability across a variety of LLMs, offering a path toward fully autonomous systems capable of handling unexpected challenges, paving the way for robust, adaptive control in complex industrial environments. To demonstrate the concept's effectiveness, we created a simple case study involving a temperature control experiment embedded on a microcontroller device, validating the proposed approach.
... The authors observed that these dynamic systems could help companies develop competitive products that enhance sustainability and business growth. These findings align with previous research by Gao, Shang, and Kokossis (Gao et al., 2009), which examined the applicability of an agent-based system for supporting decisions in a chemical production company. Felsberger, Oberegger, and Reiner (Felsberger et al., 2016) disputed the potential of intelligent system support in production planning as a function of management. ...
Manufacturing enterprises are under constant pressure to deliver quality products at the right to meet the highly dynamic needs of their customers. Given the increasingly stiff competition from both national and international enterprises on the market, manufacturing managers have no choice but to optimize their processes to increase productivity, flexibility, and responsiveness. This paper attempts to show that deploying intelligent support systems in managing manufacturing processes is crucial for the survival of manufacturing enterprises and ensuring growth and sustainable development. The study focuses on the current research related intelligent decision support systems, genetic algorithms, and artificial neural networks and how they can help optimize manufacturing processes. Manufacturing enterprises are under constant pressure to sustain growth and development in increasingly competitive business landscapes. Enhancing productivity and flexibility in manufacturing requires rapid decision-making for optimal outcomes. A review of existing works of literature identifies the significant role of a robust decision support system in process optimization. The study establishes that genetic algorithms provide better tools for strategic decision-making and hold great potential for solving process optimization challenges. Moreover, a review of existing literature on artificial neural networks present them as essential tools for decision-making through their capacity to generate optimal outputs in process optimization. The observations emphasize the ability of artificial neural networks and genetic algorithm in enriching decision support systems capable of optimizing manufacturing processes. The study shows the need for further studies on unified techniques and methodologies of their implementation in manufacturing processes.
... [3] presents an IABS specialized in solving the problem of sustainable supplier selection. [4] presents an IABS specialized in the decision support used in the chemical process industry. ...
Measuring the machine intelligence quotient (MIQ) of intelligent agent-based systems (IABSs) is very important based on the increasing number of intelligent systems applied to real-life problem solving. The most important property of an intelligence metric must be its universality. Developing universal intelligence metrics is difficult based on the very large diversity of intelligent systems. A feasible approach for ensuring the universality of measuring machine intelligence consists in using black-box-based methods able to measure the central intelligence tendency in problem solving. This paper represents a guide for choosing the most appropriate black-box-based intelligence metric for measuring the intelligence of developed IABSs, classification of IABSs in intelligence classes and detection of the IABSs with statistical low and high outlier intelligence. In research where the performance of heuristic and metaheuristic algorithms is studied, the performance indicator is frequently calculated as the mean or the median of experimental evaluation results. There is no consensus agreement regarding which of them is more appropriate. In some cases, both of them are reported. The manner in which it should be decided which of them to be used is scientifically grounded in this paper.
... In the area of process optimization there are several algorithms that have been developed to exploit parallel CPUs, including deterministic algorithms for large-scale nonlinear programming (Zavala et al., 2008;Zhou et al., 2018Zhou et al., , 2014Zhu et al., 2009), for dynamic optimization (Washington and Swartz, 2017;Word et al., 2014), for simulation (Weng et al., 2015), for stochastic optimization (Cecelja et al., 2014;Kokossis et al., 2011;Papadopoulos et al., 2016;Papadopoulos and Linke, 2009) and for optimization under uncertainty (Papadopoulos et al., 2012), to name but a few. Advanced multi-agent algorithms have also been proposed to enable intelligent decision making in parallel environments (Gao et al., 2009;Siirola et al., 2004Siirola et al., , 2003. A framework for integrated process design and control in a parallel, CPU-based infrastructure has also been reported (Miller et al., 2017), without specific references to optimizations that facilitate parallel execution. ...
A hybrid algorithm is proposed, comprising Simulated Annealing, an NLP algorithm (IPOPT) and a continuation method (PITCON) for simultaneous process design and controllability assessment. The algorithm integrates the approximate computing techniques of memoization, task dropping and loop perforation. SA and process model calculations are parallelized through skeleton programming (SkePU) and a tool for dynamic, run-time scheduling (StarPU). The same code is ported across different programming interfaces (OpenMP, CUDA, OpenCL and StarPU-SkepU MPI) and executed across different accelerators (multi-node, multi-CPU, GPU and multi-CPU-GPU). Case studies on CO2 capture system design include simultaneous solvent selection, process synthesis and controllability assessment. Up to 70% improvement is attained in the optimal solution, with up to 74% fewer unconverged model simulations. Excellent scalability is observed in 1,000 threads, attaining up to 60 times faster execution in multi-CPU, GPU and multi-CPU-GPU accelerators. A trade-off is observed between the CPU energy consumption and the execution speedup.
... In this regard, Zhang and Zhao [56] provided a model based on two dimensions of accident rates and simulated accident results to analyze the transportation risk of dangerous chemicals by using GIS technology. Gao et al. [19] demonstrated agent-based models to integrate chemical process information, process models, and assess the risk management decisions in CSC. None of the above-mentioned studies discussed the impact of transportation fleet capacity on risk. ...
The production and transportation of chemicals is a risky process with high-cost operations for members of the supply chain, where some of the materials deteriorate over time and deal with value-reduction challenges. This paper studies a two-stage hazardous chemicals supply chain with a supplier and a manufacturer in a finite time horizon with a constant deterioration rate for both sides. To prevent potential hazards and improve product quality, the manufacturer invests in risk reduction and quality improvement technologies that can also attract more market demand. Owing to the importance of time in the storage and production of chemical products, this study focuses on a novel lead-time based discount contract to coordinate the channel members. The contract seeks to maximize the total profit of the chain by determining the optimal lead-time and manufacturer's technology level. By doing so, the supplier provides high-quality products and the manufacturer's unit supplying cost reduces and can buy more chemicals from the supplier. On the other hand, the supplier will have more time to supply the product and its initial cost will be reduced. As a result, the profit of both sides increases simultaneously. Some numerical examples are applied to examine the applicability of the proposed models. Finally, several sensitivity analyses on the main parameters are conducted to extract some in-depth managerial implications.
... Les SAD sont utilisés pour résoudre de nombreux problèmes du domaine industriel. Parmi ceux-ci, on peut citer : • La régulation et la reconfiguration des réseaux de transports [Zidi (2007); Mejri (2012)] ;• Le diagnostic et la maintenance des systèmes automatisés[Hedberg et al. (2018);Gao et al. (2009)] ; ...
Les systèmes automatisés de production (SAP) représentent une classe importante desystèmes industriels qui sont devenus complexes et sensibles aux dysfonctionnements avecdes conséquences importantes sur la productivité, la qualité de production et la sécuritédes biens et des personnes. Un défi majeur est de mettre en oeuvre des approches systématiquesd’aide ou de diagnostic afin de garantir la sûreté de fonctionnement. Cette thèses’intéresse donc au diagnostic en ligne des comportements indésirables des SAP ayant descapteurs et des actionneurs délivrant des signaux binaires et dont la dynamique correspondà celle des systèmes à évènements discrets (SED).L’efficacité d’une approche de diagnostic au service de ce type de systèmes se mesure àtravers le taux de bonne détection de fautes, la précision d’isolation, le nombre de faussesalarmes et la complexité de mise en oeuvre de l’approche. L’objectif de ce travail est doncde concevoir des solutions de diagnostic intelligentes qui satisfont les critères mentionnéssans requérir la connaissance complète du fonctionnement interne du système, capablesde se mettre à jour en temps réel pour améliorer les performances et ayant un faible coûtde mise en oeuvre.L’approche proposée dans cette thèse est basée sur le Raisonnement à Partir de Cas(RàPC) qui est à la fois une méthodologie de raisonnement par analogie et une méthodologied’apprentissage issue du domaine de l’intelligence artificielle. L’originalité des travauxréside en finalité dans les quatre items suivants : (1) l’approche proposée utilise le RàPCpour le diagnostic des SAP ayant une dynamique de type SED, (2) elle propose un formatde représentation de cas inspiré du formalisme Signatures Temporelles Causales quis’adapte à l’aspect dynamique des systèmes à surveiller, (3) elle introduit une phase quicouplent simulation et mise en forme de données pour la transformation des données issuesdu système simulé après son émulation en mode normal et défaillant, et (4) elle présenteune phase de raisonnement et d’apprentissage qui permet non seulement le diagnostic enligne du système surveillé mais aussi la mise à jour de la base de cas suite à l’apparitionde nouveaux comportements inconnus.
... An agent-based model is a promising method to simulate complex systems consisting of autonomous decision-making agents [1]. During this kind of simulation, each agent acts as a single entity following its own set of characteristics in response to the conditions that the agent deals with [2][3][4]. Agent-based modeling is an applicable tool for process design which provides a natural description of a system [3]. It has been used in various application fields [5][6][7]. ...
Forward osmosis (FO), as an emerging technology, is influenced by different factors such as operating conditions, module characteristics, and membrane properties. The general aim of this study was to develop a suitable (flexible, comprehensive, and convenient to use) computational tool which is able to simulate osmosis through an asymmetric membrane oriented in pressure retarded osmosis (PRO) mode in a wide variety of scenarios. For this purpose, an agent-based model was created in NetLogo platform, which is an easy-to-use application environment with graphical visualization abilities and well suited for modeling a complex system evolving over time. The simulation results were validated with empirical data obtained from literature and a great agreement was observed. The effect of various parameters on process performance was investigated in terms of temperature, cross-flow velocity, length of the module, pure water permeability coefficient, and structural parameter of the membrane. Results demonstrated that the increase in all parameters, except structural parameter of the membrane and the length of module led to the increase of average water flux. Moreover, nine different draw solutes were selected in order to assess the influence of net bulk osmotic pressure difference between the draw solution (DS) and feed solution (FS) (known as the driving force of FO process) on water flux. Based on the findings of this paper, the performance of FO process (PRO mode) can be efficiently evaluated using the NetLogo platform.
... Some researchers have applied a rule based system to control a continuous chemical production line (Mahdavi et al., 2013, Gao et al., 2009. Since different and unexpected conditions may be happened in a chemical production line, utilizing predefined rules is the main drawback of previous works. ...
In continuous chemical production lines, final products are produced through irreversible and continuous reactions in successive departments. So, the quality of the final products depends on the quality of the input materials and departments’ situation. Any out of the control situation along a production line leads to operation time, resource and financial lost and spoiled materials. Undoubtedly, decreasing the controlling communication time between different departments and handling unexpected conditions are critical issues in such production lines. In this paper, a Fuzzy Q-learning Multi-Agent Quality Control System (FQL-MAQCS) is proposed to control a continuous chemical production line. The proposed FQL-MAQCS can control unexpected conditions by applying a multi-agent based system consisting of the quality control executor, process data analyst, central decision maker, departmental decision maker, and knowledge and rule manager agents. In addition, the proposed system is equipped with a self-learning mechanism, whose knowledge is gradually formed based on the results of the learning process and stored in the knowledge base. To this end, the fuzzy Q-learning method and rule production mechanism are used. The proposed FQL-MAQCS is tested in a real case study and the associated results demonstrate the usefulness and capability of the developed quality control system.
... Over recent years, many other applications have been developed with the purpose of increasing industrial productivity. Research carried out by Forget et al. (2008), Gao et al. (2009) and Chan et al. (2012 are examples of these applications. Furthermore, relations between the companies have also inspired many ABMs, mainly where a high number of firms is located, such as in industrial districts and clusters. ...
This article describes the main approaches adopted in a study focused on planning industrial estates on a sub-regional scale. The study was supported by an agent-based model, using firms as agents to assess the attractiveness of industrial estates. The simulation was made by the NetLogo toolkit and the environment represents a geographical space. Three scenarios and four hypotheses were used in the simulation to test the impact of different policies on the attractiveness of industrial estates. Policies were distinguished by the level of municipal coordination at which they were implemented and by the type of intervention. In the model, the attractiveness of industrial estates was based on the level of facilities, amenities, accessibility and on the price of land in each industrial estate. Firms are able to move and relocate whenever they find an attractive estate. The relocating firms were selected by their size, location and distance to an industrial estate. Results show that a coordinated policy among municipalities is the most efficient policy to promote advanced-qualified estates. In these scenarios, it was observed that more industrial estates became attractive, more firms were relocated and more vacant lots were occupied. Furthermore, the results also indicate that the promotion of widespread industrial estates with poor-quality infrastructures and amenities is an inefficient policy to attract firms.
... A multi agent robot soccer system which makes intelligent decisions through compounded artificial neural networks is presented in [23]. In 2009 Gao et al. developed an agent-based intelligent system for decision making in chemical process industry [16]. Ghijsen et al. introduced decision making frameworks that enable the agents of a system to select the best coordination mechanism (centralized and decentralized) in a given situation [18]. ...
Aphasia diagnosis is a challenging medical diagnostic task due to the linguistic uncertainty ad vagueness, large number of measurements with imprecision, inconsistencies in the definition Of Aphasic syndromes, natural diversity and subjectivity in test objects as well as in options of experts who diagnose the disease. In this paper we present a new self-organized multi agent system that diagnoses different types of Aphasia based on fuzzy probabilities. In the proposed multi agent system, the characteristic of self organization is employed as both a decision making feature selection paradigm as well as a mechanism to estimate the probability mass functions of Aphasia factors. The estimated probability mass functions are involved in fuzzy probability calculation of different types of Aphasia. The performance and robustness of the proposed method is compared with several earlier approaches. While the proposed method requires more of the available test parameters, the comparison clearly shows the superiority of the proposed method in terms of accuracy as well as robustness.
... Oztemel E. presented a knowledge exchange procedure for creating integrated & intelligent manufacturing system [14]. Ying G. presented agent-based intelligent system to support coordinate manufacturing execution and decision-making in chemical process industry [15]. Gang X. discussed push/pull production mode used in CIMS and its application in refinery [16], and proposed information integration method of virtual pulp & paper enterprise [17]. ...
Global manufacturing enterprises meet a lot of challenges on enterprise level, plant level and shop floor level. To solve those challenges, a kind of real- time Manufacturing Integration and Intelligence (Mil) solution is proposed, and its standard interfaces with ERP modules and shop floor systems, standard integration functionalities, and typical use cases and typical benefits, are described. By using of the practical project executed in one global chemical company as background, the paper introduces the project's "AS IS" situation, and "TO BE" target. Then, the Mil solution is discussed in more detail, including its business scope, customer requirements, server selection, high availability solution, core technologies, and its main functions: load; unload; transfer; special instruction; inventory; blending; KPI dashboard. The tactical benefits, which have been made for the customer with the Mil solution, are summarized. Finally, some conclusions are drawn out.
... Oztemel E. presented a knowledge exchange procedure for creating integrated & intelligent manufacturing system [28]. Ying G. presented agent-based intelligent system to support coordinate manufacturing execution and decision-making in chemical process industry [29]. Gang X. Discussed push/pull production mode used in CIMS and its application in refinery [30], and proposed information integration method of virtual pulp & paper enterprise [31]. ...
A flexible manufacturing system (FMS) is a manufacturing system in which there is the capability of handling the variations in product’s features that is the result of ever-changing customer demands. The flexibility attributes to utilize the resources in a more effective manner. On the other hand, the control of such systems would become more complicated and challenging. FMS needs CNC machines and robots and other resources for establishing the flexibility and enhancing the efficiency of the whole system. Also it needs to integrate the resources to reach flexibility. To reach this goal, an integrator framework is presented for implementing loading and unloading tasks by industrial robots. At the first step, the machining data of CNC machine is received in a STEP-NC file. Then the information system as one of framework’s components, processes the required information and provides the interoperability of the equipment. Since there is so far even no standardized information model available for exchanging data and controlling in industrial robots, in this paper we have proposed a mechanism with an STEP compliant data model in an object-oriented architecture that is used through the knowledge-based framework. The framework is connected to a database which is filled with equipment’s control commands. The framework also uses its knowledge to program the robots and control their interactions with CNC machines for loading and unloading actions. As a result, the proposed framework improves the integration of manufacturing resources in Flexible Manufacturing Systems.
... This system simulated the operations during the lifecycle of the plant allowing designers to choose alternate control system designs. Gao, Shang, and Kokossis (2009) proposed a multi agent system for information integration and decision making. This system included agents that monitored specific parameters during process operation. ...
Offshore oil and gas production platforms are uniquely hazardous in that operating personnel have to work in a perilous environment surrounded by extremely flammable hydrocarbons. A failure in an equipment could quickly propagate to others resulting in leaks, fires and explosions. Such accidents could be prevented by deploying intelligent monitoring tools which continuously supervise the process and the health of equipments to provide contextspecific decision support to operators during safety-critical situations.
Offshore production is a complex activity and no single FDI approach is suited to deal with all the possible failure scenarios. For instance, offshore platforms are characterized by several instrumentation and equipment level failures. Monitoring the overall process for detecting faults is not adequate as deviations in these are lagging indicators and the fault may be detected too late by which time platform safety may be compromised. However, different deviations are not independent and results from various instruments and equipment-level monitoring algorithms have to be combined considering the process connectivity and flows. Hence multiple levels of monitoring algorithms, ranging from the incipient detection of equipment related faults to process level faults for detecting human errors are necessary. We therefore propose an agent-based approach to collaboratively monitor offshore oil and gas production processes.
We have previously developed a Message Passing Interface (MPI) based architecture called CAMEO. In this work, its extension called ENCORE is reported. ENCORE uses an ontology to explicitly capture the hierarchy of the offshore platform, comprising the entire process at the highest level to the individual instruments and equipment at the lowest. Similar to CAMEO, each FDI method in ENCORE is modeled as an Agent. Each FDI agent can specialize in monitoring a different aspect at varying levels of granularity (tag level to unit level), scope, and monitoring methodology.
A key issue in monitoring any complex system using multiple independent methods in parallel is that the individual agents may not always concur. In this work, a consolidator agent is hence developed. The consolidator agent performs the matching between the results from the various FDI agents by mapping their evidences to the process ontology and seeking coherence among the various evidences using voting, Bayesian probability and Dempster-Shafer fusion strategies.
Finally, offshore platforms operate in a dynamic environment with numerous state changes (due to maintenance activities such as pig-launching, corrosion inhibitor injection, kinetic hydrate inhibitor injection etc) and disturbances. To effectively monitor the process, the FDI agents and the consolidator agents have to learn and adapt to the current conditions. Agents in ENCORE have this ability to continuously adapt to process and system changes as well as improve their innate data-based models by observing the outputs and maps of other agents.
ENCORE agents are compliant with the FIPA (Foundation of Intelligent Physical Agents) specifications; hence they can co-exist and cooperate with other agents developed in other implementation packages as well. The current implementation is also inherently multi-threaded; hence it can seamlessly scale-out to additional processors as computational load of monitoring increases during abnormal situations.
The multi agent framework as implemented using JADE (Java Agent DEvelopment Framework), in which the results of several FDI agents, each specialized in monitoring certain aspects of the overall process, are meaningfully fused by a consolidator agent based on the process ontology is demonstrated in this paper. Comparisons of the monitoring performance against other monolithic approaches are also shown.
References
Ng Y. S., and Srinivasan R., (2007). Multi-agent Framework for Fault Detection and Diagnosis in Transient Operations, Presented at the European Symposium on Computer Aided Process Engineering, Bucharest, Romania, Paper T1-474.
... Adhitya et al. develop hybrid optimization and ABM techniques for managing disruptions to supply chains. More examples of agent-based modeling of chemical supply chains, some of which specifically target disruption management, can be found in Srinivasan, Bansal, and Karimi (2006), Gao, Shang, andKokossis (2009), van Dam, Lukszo, andSrinivasan (2009), Aslam and Ng (2010), Mishra, Kumar, and Chan (2010), Giannakis andLouis (2011), andSinha, Aditya, Tiwari, andChan (2011). None of these, however, attempt to model the plantlevel components and whole-system dynamics of large chemical supply chains. ...
... This system simulated the operations during the lifecycle of the plant allowing designers to choose alternate control system designs. Gao, Shang, and Kokossis (2009) proposed a multi agent system for information integration and decision making. This system included agents that monitored specific parameters during process operation. ...
Modern chemical plants have evolved into extremely large and complex operations. Operators rely on the plant automation system, particularly the DCS, for managing the plant operations which themselves have become open, and involve multiple third-party technologies, instruments, and software. The structural-, scale- and dynamic-complexity makes it challenging for operators to infer the conditions in the plant quickly and make timely decisions, especially during abnormal situations. A process supervision system that assists the operators by providing holistic decision support is therefore essential. Here, we propose an multi agents based architecture for supervision of large-scale chemical plants. The key insight in the proposed architecture is that the process descriptors used for developing the supervision models themselves are not static and change routinely. The proposed architecture uses an ontology to represent all the process descriptors formally, so that any changes can be captured and their effects propagated seamlessly. This architecture has been implemented as a multi agent system called ENCORE. The detailed implementation of ENCORE is presented and its benefits are illustrated through an offshore oil and gas production case study.
... Learning (Bergadano et al., 1999;Anumba et al., 2002;Tweedale et al., 2007;Chang, 2008;Biswas, 2008;Keegan, O'Hare, & O'Grady, 2008;Saarloos et al., 2008;Montano et al., 2008;Gao, Shang, & Kokossis, 2009;Zunino & Campo, 2009;Guo & Zhang, 2010). ...
E-learning is one of the most important learning approaches within which intelligent software agents can be efficiently used so as to automate and facilitate the process of learning. The aim of this paper is to illustrate a comprehensive categorization of intelligent software agent features, which is valuable for being deployed in the virtual world of learning and training. The characteristics of agents make them worthwhile for being used in the implementation and improvement of e-learning information systems, especially the web-based or web-enabled e-learning mechanisms. An extensive exploration of agent-related international papers has been conducted so as to cover a wide range of internationally accepted features as well as the classification of agents and their correspondent references. These agent characteristics enable the online learning mechanisms to act on behalf of the user in electronic learning and to respond to specific requirements in a more efficient and effective manner than the traditional learning systems. The implementation of agents according to the most useful features helps teachers transfer the related knowledge easier, faster, and more directed towards the targeted audience of the e-learning system for a better and deeper learning quality.
A variety of optimization tools are used in the chemical industry, but they are often embedded in inflexible, isolated, manual, and complex decision‐making processes. This work proposes a decision‐making framework that integrates models, data, and decision‐makers into data‐connected decision cells, organized within a decision graph. The framework formalizes decision processes and enables systematic and adaptive workflows across decision layers. The framework can be applied to various use cases, including supply chain optimization and process design, to address the evolving challenges of the chemical industry. It enables a shift from component‐level optimizations toward system‐wide optimization strategies that account for the interconnected nature of complex production systems.
The technologies of Industry 4.0 provide great improvements in the productive environment of the continuous process chemical industries. The availability of a large amount of real-time data allows the integration of unit operations and process intensification, providing increased profitability, improving fault predictive diagnostics, and assisting with safety management and production sustainability. However, the industry presents specific obstacles in deploying 4.0 technologies because of its instrinsic complexity. The objective of this work is to point out the sector-specific difficulties, Critical Success Factors and benefits when implementing Industry 4.0 technologies. In order to achieve this objective, a comprehensive PRISMA systematic review of the literature was carried out, in which more than 10000 documents were analyzed, from Google Achademics® and Scopus. Some implementation challenges are the development of reliable fault response systems for high risk processes and the scarcity of deployment success cases. Among the emerging necessities identified for the sector, the concern to simplify complex systems and intensify operations is highlighted. The literature also converges on Critical Success Factors, such as the creation of reliable measurement, transmission and data collection systems and health, safety and environmental assessment models. Among the benefits are the improved management of hazardous products and improvements in resource management and energy efficiency. The evolution of the industry in the face of the innovations of Industry 4.0 is evidenced and future research opportunities are presented in the area.The study is aimed at managers of the sector, who seek information for implementing 4.0 technologies, and also for researchers looking for new topics in the area. Future research opportunities in the area are also presented. The study shows the evolution of the industry in the face of Industry 4.0 innovations.
Cette thèse a pour objectif principal de développer un simulateur multi-agents pour concevoir un système d'aide à la maitrise des risques des activités de maintenance. Le but est d'explorer la complexité de la maintenance et de spécifier les interactions entre la fonction maintenance, l'analyse et l'évaluation des risques. Nous nous intéressons d’une part, à concevoir un modèle systémique permettant d’identifier et de modéliser un système industriel, à montrer les différentes interactions entre ses éléments, à analyser et évaluer les risques des activités de maintenance. Nous proposons la méthode MOSAR et le langage UML pour concevoir un modèle cognitif de référence. Ce modèle a servi de point de départ pour la conception d’une base de données à l’aide du langage SQL, qui est exploitée par le modèle Multi-Agents afin d’acquérir les informations nécessaires à son fonctionnement.D’autre part, nous développons une architecture d’un Système Multi-Agents qui a pour vocation d’anticiper les situations de défaillances et la prise de décisions à l’aide de la simulation du comportement du système étudié. Une comparaison entre les plateformes existantes dédiées aux Systèmes Multi-Agents est effectuée pour choisir la plateforme adéquate à notre problématique pour la réalisation de la simulation.Finalement, les modèles développés sont appliqués dans le cadre d’une chaîne logistique pour le chargement et le déchargement de GPL (Gaz de Pétrole Liquéfié). Un simulateur a été développé à l’aide de la plateforme AnyLogic dans le but d’étudier le comportement du système et de simuler les scénarios de défaillances choisis par l’industriel pour le calcul de la criticité à partir de trois paramètres (fréquence, gravité, détectabilité) et l’obtention d’un Tableau de Bord contenant un ensemble d’indicateurs de performance de la maintenance. Les modèles de simulation proposés permettent d’orienter les industries vers les bonnes décisions pour éviter les situations à risques pouvant déclencher des événements perturbateurs dommageables.
Cruise tourism represents a strategic sector for the economic growth of several countries, impacting on different direct and indirect markets. The arrival of cruises in a city represents an unmissable opportunity to increment its tourist market penetration. Nevertheless, the management of an unforeseen number of passengers that need to visit a city in a short time may also have a negative impact, so reducing the expected benefits. This is mainly due to the difficulty of taking the right decisions when organizing the dispatching of passengers in different city areas since these decisions depend on several conditions that can also dynamically occur, and may have an impact on different city sectors. Here, a decision support system is proposed to help involved stakeholders to make decisions to plan passengers' transportation in the city and also to evaluate the consequences for the city if the plans are really implemented. The system is designed according to the multi-agent paradigm, so allowing one to easily manage the necessary coordination among different entities and data sources that are usually distributed and need to cooperate to provide useful suggestions. In addition, a prototype of a web-based application is provided to end users, so that it can run on heterogeneous platforms, and it can be easily accessed by different users from different devices, as it is the case for the considered application domain.
This chapter investigates the use of multiobjective optimization to support integrated molecular and process design in two new research frontiers pertaining to efficient process operation as well as computations in grid and cloud computing environments. In the first frontier, we propose a new framework supporting the integration of molecular design and selection with process operation at conditions other than the nominal design settings. The framework combines multiobjective decision-making with a systematic nonlinear sensitivity analysis approach to identify molecular and process characteristics that exhibit reduced sensitivity to external or internal process variability. In the second frontier, we propose the use of this framework in advanced grid and cloud computing environments to improve the efficiency of the necessary computations and to support automated decision-making through user interfaces and workflows that allow the interoperation of heterogeneous design tools. The proposed framework is offered in a software-as-a-service approach where molecular and process design tools as well as multiobjective decision making and sensitivity analysis tools exploit distributed resources under the coordination of dedicated middleware services accessed through a web interface. The proposed developments are illustrated through applications in heat-to-power generation systems (Organic Rankine Cycles) and industrial separations.
The arrival of cruises in a city represents an unmissable opportunity for the city economy to increment its tourist market penetration. Nevertheless, the management of an unforeseen number of passengers that need to visit the city in short time may have a negative impact on the city, so reducing the expected benefits. This is mainly due to the difficult in taking the right decisions when organizing the dispatching of passengers in different city areas, since these decisions depend on several conditions, that can also dynamically occur, and may impact different city sectors. In order to address the problem of organizing transportation and city tours for cruise passengers in a city, a Decision Support System is proposed to help both planning passengers transportation in the city, and also to evaluate the consequences for the city if the plans are really implemented. The system is designed according to the multi-agent paradigm, so allowing to easily manage the necessary coordination among different entities and data sources that are usually involved in the considered application domain.
Unforeseen events can interrupt the operational process and have a negative impact on the chemical supply chain transportation (CSCT) system. A number of research studies have addressed the risk management issues in chemical supply chain (CSC) or CSCT. However, most of the existing methodologies lack inbuilt and practical techniques that take into consideration the complex interactions and dynamic feedback effects, which can significantly affect the reliability of risk management outcomes. This paper suggests a novel modelling and simulation method to address the dynamic risks effects in the CSCT, especially the consideration of time-dependent system behaviour in different operational conditions. Furthermore, the flexibility of the model modification is adapted to enhance the practice in risk mitigation. A transparent decision support tool is provided to compare the outcomes of different risk mitigation processes, which offers decision makers an alternative CSCRM mitigation package.
Currently, to keep the competitive edge, firms focus on the improvement of the decision making and use different management information systems to leverage the process. In this study, it has been designed an information system which aims to support the management of human resources in the small and medium sized enterprises in Turkey. To do this, a group of human resource key point indicators have been determined for a system design which includes Mysql- and Java-based Hibernate Criteria Api, search algorithm, relational database, JSF(java server faces) Framework and Primefaces structures as methodology. It has been demonstrated by sample user interface snapshots and analysis of the system benefits that the system would serve decision makers in a number of areas including training, performance, efficiency, workforce and working time supported by its user friendly characteristics such as; real time analysis, decision making opportunities and flexibility of accessibility it offers to small and medium sized enterprises.
This chapter presents the latest IDSSs, such as text analytics and mining based DSSs; ambient intelligence and the internet of things-based DSSs; biometrics-based DSSs; recommender, advisory and expert systems; data mining, data analytics, neural networks, remote sensing and their integration with decision support systems and other IDSSs. These other IDSSs include GA-based DSS; fuzzy sets DSS; rough sets-based DSS; intelligent agent-assisted DSS; process mining integration to decision support, adaptive DSS; computer vision based DSS; sensory DSS and robotic DSS. In addition to acquainting these IDSSs, author introduce practical examples where they have been effectively applied.
The article contains sections titled: 1. Dawn of the Data-Rich Era 2. From Data to Knowledge to Decisions 3. Cyberinfrastructure: Current Trends and Future Outlook 3.1. General Purpose Tools and Environments 3.2. Recent Progress in some Application Domains of Chemical Engineers 4. Decision Support Systems 5. Summary 6. Acknowledgments
Agent based models (ABM) have been recently applied to solve optimization problems whose domains present several inter-related components in a distributed and heterogeneous environment.In this work we illustrate the state of the art related to the use and to the application of ABM as optimization technique, given their peculiarity in dealing with the representation and the simulation of complex systems.After a description of the approach and a comparison with classical heuristics, an extensive review aimed at evaluating the impact of these methodologies in the Operational Research/Management Science literature is provided.
In the shipbuilding process, a number of ship specification files are generated. Those files are usually scattered as different file formats in various departments or stored as databases in the heterogeneous systems within a shipyard. Therefore, it is extremely difficult to integrate specification files coming from different stages of shipbuilding, much less to share the integrated information among various departments. Moreover, long-term accumulation of files and continuous expansion of computer systems place a heavy burden on the shipyard, for it must invest more capital in software development and hardware. To address this problem, this study proposed the concept of cloud services. Specifically, the authors constructed a cloud-based, service-oriented and knowledge-sharing architecture which was founded on XML and Web Services technology. Through the newly developed architecture, ship specification files can be structurally integrated and preserved; meanwhile, they can be conveniently transmitted among the heterogeneous systems, with openness between different systems achieved. Thus, all knowledge owned by the shipyard will be efficiently managed, applied and shared. In addition, the shipyard may reduce its investment in IT equipment, including software development and hardware peripherals.
In reality, traditional process control system built upon centralized and hierarchical structures presents a weak response to change and is easy to shut down by single failure. Aiming at these problems, a new agent-based service-oriented integration architecture was proposed for chemical process automation system. Web services were dynamically orchestrated on the internet and agent behaviors were built in them. Data analysis, model, optimization, control, fault diagnosis and so on were capsuled into different web services. Agents were used for service compositions by negotiation. A prototype system of poly (ethylene terephthalate) process automation was used as the case study to demonstrate the validation of the integration.
The joint application of web services and intelligent software agents leads to the creation of intelligent web services. Applying intelligent software agents (ISAs) would increase the capability of website administrators in responding to the user's needs at the right time and with high quality and safety. This paper intends to develop a conceptual framework through a comprehensive investigation of the broad literature of ISAs so as to assist the developers in designing and optimising the web services. The main goal of this paper is to represent a comprehensive framework based on the collection and classification of important services of websites as well as categorising the ISAs in order to be utilised in implementing these important services in order to improve the quality of service usage. This classification is based on a deep and complete review of the most applicable services in websites through the study of the top one hundred websites' services of the world through the most visited websites. Describing the classification of agents and their significant features has led to the identification of the main intelligent agents for implementing the services of websites in order to optimise the usage of such services.
The main purpose of this paper is to illustrate a pervasively explored literature-based categorisation of intelligent software agents and present a new taxonomy of them through the definition of ontology for helping and guiding the future research, both in theory and practice, toward coherence. The process of category building has undergone a broad literature review of various related papers and academic works. The aim of the categorisation has been the extraction of an encompassing ontology which covers a wide range of internationally accepted types of agents and their corresponding features in order for the researchers to apply them into the appropriate context as required. Such ontology considerably helps the academic scholars in developing the related literature based on the firm ground provided and it will also contribute to the practitioners in developing multi-agent systems based on the similarities, differences, and cross-functional features and characteristics of intelligent software agents provided in the ontology of agent categories and features.
An online platform focusing on intermediary transaction can provide its users with needed products and services. Also, it can be used to collect, exchange, and integrate product information which involves design, production, and marketing, as well as consumer feedback. Currently, it is rather difficult to integrate and share the knowledge coming from different stages of product development. In view of that, we have employed the service-oriented architecture (SOA) to construct a design-centric, Web-intermediary, and knowledge-sharing platform (DWKSP). The platform in question integrates all product samples belonging to different users. Moreover, it serves as the underlying infrastructure which communicates and transmits product information. Through Extensible Markup Language (XML) technology, different fields of knowledge are integrated into the programmed procedure of an Internet-mediated transaction (IMT). Such knowledge is closely connected with designing, manufacturing, and marketing a particular product. Consequently, the knowledge accumulated during an IMT will be structurally preserved; later, it will be transmitted between the users' heterogeneous systems. As the specification files of the product are shared by different users, the goal of integrating heterogeneous data is achieved. © 2012 Wiley Periodicals, Inc. Syst Eng 15
Intelligent Manufacturing System (IMS) shall be considered as a system integrated with different intelligent subsystems, which completes the distributed solution procedure on the basis of exchanging large quantities of materials, energy and information. Any intelligent manufacturing process self-regulates and self-controls itself in manufacturing the products within the design specifications. It incorporates introduction of human-like decision-making capabilities into the manufacturing system that brings the intelligence. The system however requires complete information of the requirements and processing of production system to generate appropriate decisions. This paper provides a comprehensive review of research on web-enabled e-Manufacturing technology which bridges certain aspects of manufacturing system like Customer Relationship Management (CRM), Enterprise Resource Planning (ERP), and Supply Chain Management (SCM). Web-based systems have been implemented to provide remote service and manufacturing for rapid prototyping, enhance the availability of facilities and improve the capability of rapid product development for various enterprises. Web-based technique is utilized to derive the availability of information anytime, anywhere and by the persons who are authorized to deal with it. The e-Manufacturing production system can substantially reduce product cost and delivery cycle for manufacturing systems.
Multi-agent system (MAS) is a set of intelligent agents which can perform common tasks by communicating, cooperating and collaborating with each other. It has the abilities of self-organization, self-learning and self-reasoning. In recent years, MAS is one of the hot researches in the field of distributed artificial intelligence. It is widely used in various aspects of the social field and provides a new idea for complex system. This paper firstly has a review to introduce multi-agent technique implemented in many social fields to show its extensive usability in different social fields and well ability to solve different complex problems. Petroleum production processes possess the characteristics of complexity, multi-variables and uncertainty etc. Traditional production techniques in petroleum field have faced lots of limitations in modern environment. It is necessary to adopt advanced and appropriate methods to improve production techniques. As a well theory for solving complex problems, MAS is utilized by more and more researchers to deal with different difficult problems in petroleum production processes.
Global manufacturing companies meet a lot of challenges on enterprise level, plant level and shop floor level. To solve these challenges, a kind of real-time Manufacturing Integration and Intelligence (xMII) Solution is introduced to realize Adaptive Manufacturing (AM), where MII's key technologies, such as its connection with ERP modules, integration functionality with shop floor information technology (IT) systems, and xMII server, are generally described. By using the practical project executed in one global chemical company as background, the paper firstly introduces the project's “AS IS” situations, its “TO BE” targets, and its ERP solution. Then, MII solution of the project is discussed in more details, which include its business scopes, requirements, server selection, high availability solution, its technologies, and its main functions like Unloads, Customer Response Time. Finally, tactical benefits of this MII solution are listed, and some conclusions are drawn out.
Water price forecasting is a very important and difficult decision-making issue of any water resource decision support systems. Because there are many factors that would affect the price of water resource, there aren't any accurate models, which can be used in the water price forecasting. In this paper, an intelligent decision support system based on multi-agent is set up and applied to water price forecasting. An improved reinforcement learning approach is proposed to realize the multi-agent cooperation in the intelligent decision support system. In the proposed approach, a dimension reduction algorithm is used, which make the proposed approach have some good performances, such as the higher learning speed, the better convergence performance, and the better practicability. The experimental results show that the proposed approach can deal with the water price forecasting correctly and quickly.
Due date (DD) quotation for the customer enquiry is strategically important in the mould industry, having a large influence on the delivery reliability performance. This paper develops a multi-agent system framework (MASF), which uses a multi-agent system to provide a reliable and competitive DD for the new arriving orders. Firstly, a decision-making structure for mould DD quotation is proposed, which can determine reasonable delivery times or reject the unsuitable orders. Compared with previous research, a distinguishing feature of the structure is to take into consideration the uncertainties of resources for processing task via a stochastic state evolution model (SSEM). Based on the presented structure, the MASF is then developed and described using six different agents. The algorithm agent (AA) is the key to the framework and contains two models: capacity check model and project progress evolution model. The former is used for verifying the feasibility of the fixed DD, and that the latter can compute the probability distribution and mathematical expectation of the negotiable DD. Other agents are responsible for providing necessary information to the AA. Finally, a numerical example of a real-life mould production system is studied and shown to be more suitable for a stochastic environment than related research.
Order acceptance under uncertainty is a challenging problem in supply chain management, especially in make-to-order plants, such as in a specialty chemical manufacturing enterprise. In this work, we consider the effect of rush orders and design a negotiation-based policy for order acceptance. Rush orders pose a complex challenge primarily because the different actors involved (customer and enterprise) have different interests and asymmetric information. In addition, the interaction involves uncertainties both in the short- and long-term. To capture the rich complexity of the problem and provide a conceptual basis for developing agent-based models for such negotiation situation, this paper presents a general framework for negotiation and illustrates it using the customer-enterprise rush order due date negotiation case. On the basis of this framework, an agent-based model is developed. Various experiments are conducted to evaluate the effect of due date negotiation on profit and long-term customer behavior.
Agent-based distributed simulations are confronted with load imbalance problem, which significantly affects simulation performance. Dynamic load balancing can be effective in decreasing simulation execution time and improving simulation performance. The characteristics of multi-agent systems and time synchronization mechanisms make the traditional dynamic load balancing approaches not suitable for dynamic load balancing in agent-based distributed simulations. In this paper, an adaptive dynamic load balancing model in agent-based distributed simulations is proposed. Due to the complexity and huge time consuming for solving the model, a distributed approximate optimized scheduling algorithm with partial information (DAOSAPI) is proposed. It integrates the distributed mode, approximate optimization and agent set scheduling approach. Finally, experiments are conducted to verify the efficiency of the proposed algorithm and the simulation performance under dynamic agent scheduling. The experiments indicate that DAOSPI has the advantage of short execution time in large-scale agent scheduling, and the distributed simulation performance under this dynamic agent scheduling outperforms that under static random agent distribution.
In the shipbuilding process, the information flow connected with ship specification files is very complex. These files are usually scattered as different file formats in various departments or stored as a database in the heterogeneous systems within a shipyard. Therefore, it is extremely difficult to integrate the information coming from different stages of shipbuilding, much less to share integrated information among various departments. To address that problem, the authors employ the service-oriented architecture concept to develop the knowledge-sharing architecture for ship specifications (KSASS). Equipped with extensible mark-up language and Web services technology, the KSASS is used to integrate the outline, full and construction specification files, which originate from three phases of shipbuilding. In this way, the database of ship specifications is established which is easily accessible and highly interoperable. The integrated specification files can not only be structurally preserved but also conveniently transmitted among the heterogeneous systems, with the open system achieved. Eventually, the knowledge owned by the shipyard will be efficiently managed, applied and shared.
The Web-intermediary transaction platform can provide its users with needed products and services. Also, it can be used to collect, exchange, and integrate knowledge. During an intermediary transaction, the product information involves design, production, marketing, as well as consumer feedback. However, it is rather difficult to integrate and share the knowledge coming from different stages of product development. In view of that, the service-oriented architecture (SOA) is employed to construct a design-centric, Web-intermediary, and knowledge-sharing platform (DWKSP). The platform integrates all the product samples belonging to different users. Moreover, the intermediary mechanism for product samples serves as the underlying infrastructure which communicates and transmits information. Through extensible markup language (XML) technology, different fields of knowledge are integrated into the programmed procedure of an Internet-mediated transaction (IMT). Such knowledge is closely connected with designing, manufacturing and marketing the product. In consequence, the knowledge accumulated during an IMT will be structurally preserved; later, it will be transmitted between the users' heterogeneous systems. As the specification files of the product are used uniformly, the goal of integrating heterogeneous data is achieved.
The agents and multiagent systems technology is ac- tivelyresearchedbytheacademiaandindustrialcommunity.How- ever, the technology is particularly popular in the manufacturing domain, while the applications in other domains of industrial con- trol are scarce. This survey focuses exclusively on the technology applications in the automation of continuous industrial processes, as the differences in the technology adoption between the process automation and manufacturing are significant. A large part of the literature on the subject is reviewed. The analysis of the literature is provided from several points of view, the main trends of research are described, including the shift of the researchers' interest from the agent-based supervisory control to the low-level agent-based control algorithms. Conclusions are provided regarding the lack of the technology support on the part of control instrumentation ven- dors; probable directions of the development are indicated, which turn out to be especially promising in the domain of biotechnolog- ical processes.
This paper describes the main features of an agent-based application that provides medical services to users. The system contains agents that give information about the medical centres, departments and doctors of a city. These units coordinate their execution in order to offer to the user diverse functionalities such as searching for a medical centre, accessing the medical record or booking a visit to be examined by a doctor. Special attention has been paid to the implementation of security mechanisms that guarantee confidentiality in the access and transmission of data.
Agent-based systems technology has generated lots of excitement in recent years because of its promise as a new paradigm for conceptualizing, designing, and implementing software systems. This promise is particularly attractive for creating software that operates in environments that are distributed and open, such as the internet. Currently, the great majority of agent-based systems consist of a single agent. However, as the technology matures and addresses increasingly complex applications, the need for systems that consist of multiple agents that communicate in a peer-to-peer fashion is becoming apparent. Central to the design and effective operation of such multiagent systems (MASs) are a core set of issues and research questions that have been studied over the years by the distributed AI community. In this article, I present some of the critical notions in MASs and the research work that has addressed them. I organize these notions around the concept of problem-solving coherence, which I believe is one of the most critical overall characteristics that an MAS should exhibit.
Archon provides a software framework that assists interaction
between the subcomponents of a distributed AI application, and a design
methodology that helps structure these interactions. The Archon project
has been applied to several real world industrial applications. Two of
these applications, electricity transportation management and particle
accelerator control, have run online in the organizations for which they
were developed-Iberdrola, a Spanish electric utility, and the European
Laboratory for Particle Physics (CERN). Archon's problem solving
entities are called agents; they can control their own problem solving
and interact with other community members. The interactions typically
involve agents cooperating and communicating with one another to enhance
their individual problem solving and to better solve the overall
application problem. Each agent consists of an Archon layer and an
application program (known as an intelligent system)
The Palo Alto Collaborative Testbed (PACT), a concurrent engineering infrastructure that encompasses multiple sites, subsystems, and disciplines, is discussed. The PACT systems include NVisage, a distributed knowledge-based integration environment for design tools; DME (Device Modeling Environment), a model formulation and simulation environment; Next-Cut, a mechanical design and process planning system; and Designworld, a digital electronics design, simulation, assembly, and testing system. The motivations for PACT and the significance of the approach for concurrent engineering is discussed. Initial experiments in distributed simulation and incremental redesign are reviewed, and PACT's agent-based architecture and lessons learned from the PACT experiments are described.< >
This paper presents a real-world application of a multi-agent system to enterprise integration for manufacturing planning and execution. The production management system used by most manufacturers today is comprised of disconnected planning and execution processes, and lacks the support for interoperability needed for enterprise wide integration. This situation often prevents the manufacturer from fully exploring market opportunities in a timely fashion. To address this problem, we propose an agent-based framework for intelligent enterprise integration. A set of agents with specialized expertise can be quickly assembled to help with the gathering of relevant information and knowledge, to cooperate with each other and with other parts of the management system and humans to arrive at timely decisions in dealing with various enterprise scenarios. The proposed multi-agent system, including its architecture and implementation are presented. The work of this system is demonstrated through an...
Over the last few years, the application of the agent/multiagent system paradigm seems appropriate for solving complex problems which require intelligence and bounded response times. This paper presents SIMBA: an architecture based on ARTIS agents as its main component for the development of real-time multiagent systems. The ARTIS agent architecture guarantees an agent response that satisfies all its critical temporal restrictions in a real-time environment. The main feature of SIMBA systems is their applicability for complex, distributed, real-time domains. The architecture allows the communication among agents taking into account their hard temporal restrictions. Also, the SIMBA architecture is open, allowing the interaction with external agents or FIPA-compliant agent platforms and o#ering temporallybounded services.
In this paper a novel approach concerned with the general framework of Information Management, is presented. We use a Multi-Agent System to cope with the problem of Distributed Information Retrieval. The Distributed Information Retrieval task deals with the collection of information from multiple and usually heterogeneous information sources that exist in a distributed environment, which in our case is the World Wide Web. 1 Overview of the system's architecture The advent of large wide-area networks, Internet is the most characteristic example, has caused a vast increase both in the information availability and in the number of the information sources. This evolution offers great promise for obtaining and sharing diverse information conveniently. However, the multitude, diversity and the dynamic nature of on-line information sources make accessing any specific piece of information an extremely difficult task. One way to address these issues is to use information agents. These Distri...
The software world is one of great richness and diversity. Many thousands of software products are available to users today, providing a wide variety of information and services in a wide variety of domains. While most of these programs provide their users with significant value when used in isolation, there is increasing demand for programs that can interoperate - that is exchange information and services with other programs and thereby solve problems that cannot be solved alone. The important questions raised by agent-based software engineering are enumerated in the paper.
Agent software is a rapidly developing area of research. However, the overuse of the word “agent” has tended to mask the fact that, in reality, there is a truly heterogeneous body of research being carried out under this banner. This overview paper presents a typology of agents. Next, it places agents in context, defines them and then goes on, inter alia, to overview critically the rationales, hypotheses, goals, challenges and state-of-the-art demonstrators of the various agent types in our typology. Hence, it attempts to make explicit much of what is usually implicit in the agents literature. It also proceeds to overview some other general issues which pertain to all the types of agents in the typology. This paper largely reviews software agents, and it also contains some strong opinions that are not necessarily widely accepted by the agent community.
The refinery business involves tasks spanning across several departments and requiring close coordination and collaboration among them. Present-day business decision support systems are tuned to individual departments and their work processes and are incapable of exploiting the intricate interdependencies among them. There is a need for a decision support system that provides a structured way to make decisions at the enterprise level. In this paper, we address this critical need by developing an agent-based decision support system for refinery supply chain management. Software agents are used to emulate the internal departments of the refinery. These agents gather relevant information from across the enterprise, make decisions based on the embedded business policies and mimic the different business processes of the modeled enterprise. Uncertainties in decision-making are captured by stochastic elements embedded in the agents. Through this, the dynamics in the supply chain is emulated and the performance of the supply chain measured through department-specific key performance indicators.
Modern chemical production is customer-driven and the desired delivery time for the products is often shorter than their
campaign length. In addition, the raw materials supplying time is often long. These features make it desirable to provide
tools to support collaborative supply chain decision making, preferably over the Internet, and where there are conflicts,
compromise decisions can be quickly reached and the effects of the decisions can be quantitatively simulated. This paper des
cribes such a multi-agent system (MAS) that can be used to simulate the dynamic behaviour and support the management of chemical
supply chains over the Internet. Geographically distributed retailers, logistics, warehouses, plants and raw material suppliers
are modelled as an open and re-configurable network of co-operative agents, each performing one or more supply chain functions.
Communication between agents is made through the common agent communication language KQML (knowledge query message language).
A t the simulation layer, the MAS allows distributed simulation of the chain behaviour dynamically, so that compromise decisions
can be rapidly and quantitatively evaluated. Because in a chemical supply chain the scheduling of the plant often dominates
the chain performance, an optimum scheduling system for batch plants is integrated into the MAS. The functions of the system
are illustrated by reference to a case study for the supply and manufacture using a multi-purpose batch plant of paints and
coatings.
This paper describes the application of self-optimizing control to a large-scale process, the HDA plant. The idea is to select controlled variables which when kept constant lead to minimum economic loss. First, the optimal active constraints need to be controlled. Next, controlled variables need to be found for the remaining unconstrained degrees of freedom. In order to avoid the combinatorial problem related to the selection of outputs/measurements for such large plants, a local (linear) analysis based on singular value decomposition (SVD) is used for pre-screening. This is followed by a more detailed analysis using the nonlinear model. Note that a steady-state model, in this case one built in Aspen PlusTM, is sufficient for selecting controlled variables. A dynamic model is required to design and test the complete control system which include regulatory control. This is considered in the part II of the series.
In the face of highly competitive markets and constant pressure to reduce lead times, enterprises today consider supply chain management to be the key area where improvements can significantly impact the bottom line. More enterprises now consider the entire supply chain structure while taking business decisions. They try to identify and manage all critical relationships both upstream and downstream in their supply chains. Some impediments to this are that the necessary information usually resides across a multitude of resources, is ever changing, and is present in multiple formats. Most supply chain decision support systems (DSSs) are specific to an enterprise and its supply chain, and cannot be easily modified to assist other similar enterprises and industries. In this two-part paper, we propose a unified framework for modeling, monitoring and management of supply chains. The first part of the paper describes the framework while the second part illustrates its application to a refinery supply chain. The framework integrates the various elements of the supply chain such as enterprises, their production processes, the associated business data and knowledge and represents them in a unified, intelligent and object-oriented fashion. Supply chain elements are classified as entities, flows and relationships. Software agents are used to emulate the entities i.e. various enterprises and their internal departments. Flows—material and information—are modeled as objects. The framework helps to analyze the business policies with respect to different situations arising in the supply chain. We illustrate the framework by means of two case studies. A DSS for petrochemical cluster management is described together with a prototype DSS for crude procurement in a refinery.
Completion of complex engineering designs (e.g. the design of offshore oil platforms, ships, etc.) often involves a number of agents who have to share or reuse design models within a distributed environment. This article presents a knowledge sharing workbench which enables agents to share common domain knowledge, based on the problems which emerge in the design process. The workbench includes Application Programming Interfaces provided by expert system shells, an Object Request Broker, and a number of ontologies to facilitate the construction of new knowledge-based systems. In addition, the distributed knowledge acquisition tools generated by the workbench can maintain model consistency between agents when specification changes occur in any of the agents. A case study from the petrochemical industry is used to illustrate the use of workbench for the integration of a number of agents. This case study demonstrates that a process flow knowledge model in an offshore petrochemical plant, designed for operational purposes (e.g. fault diagnosis), can be reused to form part of a new knowledge-based system which generates the data for plant layout design.
JADE (Java Agent Development Framework) is a software environment to build agent systems for the management of networked information resources in compliance with the FIPA2000 specifications for interoperable intelligent multi- agent systems. The goal of JADE is to simplify development while ensuring standard compliance through a comprehensive set of system services and agents. JADE offers an agent runtime system on which implement efficient FIPA 2000 compliant multi- agent systems and supports their development through the availability of a predefined programmable agent model and of a set of management and testing tools. This paper describes the main features of the JADE system and introduces some of the most important projects based on JADE software.
A new approach for the optimisation of steam levels of total site utility systems satisfying varying utility demands is presented, accounting for interactions between total site utility systems and chemical processes. The optimisation problem involves the selection of the steam levels with respect to their temperatures. In this paper, by exploiting total site analysis techniques, a new transhipment network is developed to represent the heat flows of a total site. Base on the transhipment network representation of the total site, a general multi-period mixed-integer linear programming (MILP) model is presented for identifying the optimal steam levels of the total site utility system. By using engineering and thermodynamic knowledge, a boiler hardware model (BHM) is developed to describe the performance of boilers, and the turbine hardware model (THM) is applied for the shaft-work targeting of steam turbines. Both models are capable of predicting the real efficiency trends of the units. The application of the proposed optimisation approach is illustrated through two case studies including single operation scenario and multiple operation scenarios.
The body of available information is rapidly increasing every day. It is becoming impossible for humans to peruse all the
available information and extract the data related to a specific topic. A great deal of important information is being neglected
primarily for two major reasons. Firstly, highly relevant information is losing its true meaning within a pool of insignificant
and unauthorized information. A lot of available information is published which is of no significance and sometimes may even
be destructive and corruptive in nature. Secondly, new knowledge and discoveries are emerging quickly as we continue to progress
and new technologies emerge. It is becoming more and more difficult each day to find specific information even within a body
of authorized information.
As a solution to this problem, humans are designing software agents that will do the search for them. In this chapter, we
will discuss agent features such as environment, internal structure, mobility, communication, and cooperative work with other
agents.
Presents and reviews a framework for online simulations and predictions which are based on the combination of real-world traffic data and a multi-agent traffic flow model. The agent architecture consists of two layers which distinguish the different tasks that road users have to perform. The framework is applied to the urban road network of Duisburg and the freeway network of North Rhine-Westphalia. On the basis of historical data, heuristics are derived, which can be combined with the dynamic data of the simulations to provide a short-term traffic forecast. The necessity for an anticipatory traffic forecast, which includes decision-making and route choice behavior of the road users, is discussed.
In this paper a novel approach concerned with the general
framework of information management, is presented. We use a Multi-Agent
system to cope with the problem of distributed information retrieval.
The distributed information retrieval task deals with the collection of
information from multiple and usually heterogeneous information sources
that exist in a distributed environment, which in our case is the world
wide web
While the theoretical and experimental foundations of agent-based
systems are becoming increasingly well understood, comparatively little
effort has been devoted to understanding the everyday reality of
carrying out an agent-based development project. As a result, agent
system developers needlessly repeat the same mistakes. At best, this
wastes resources; at worst, projects fail. The authors identify the main
pitfalls awaiting the agent system developer and recommend ways to avoid
or rectify them where possible
Effective information sharing and decision coordination are vital to collaborative product development and integrated manufacturing. However, typical special-purpose CAE systems tend to isolate information at tool boundaries, and typical integrated CAE systems tend to limit flexibility and process innovation. The SHADE (SHAred Dependency Engineering) project strikes a balance between these undesirable extremes by supporting reconfigurable exchange of engineering knowledge among special-purpose CAE systems. SHADE's approach has three main components: a shared knowledge representation (language and domain-specific vocabulary), protocols supporting information exchange for change notification and subscription, and facilitation services for content-directed routing and intelligent matching of information consumers and producers. 1 Introduction At the heart of effective concurrent engineering is communication. In product development, something is always changing-perhaps a design requireme...
The concept of an agent has become important in both Artificial Intelligence (AI) and mainstream computer science. Our aim in this paper is to point the reader at what we perceive to be the most important theoretical and practical issues associated with the design and construction of intelligent agents. For convenience, we divide these issues into three areas (though as the reader will see, the divisions are at times somewhat arbitrary). Agent theory is concerned with the question of what an agent is, and the use of mathematical formalisms for representing and reasoning about the properties of agents. Agent architectures can be thought of as software engineering models of agents; researchers in this area are primarily concerned with the problem of designing software or hardware systems that will satisfy the properties specified by agent theorists. Finally, agent languages are software systems for programming and experimenting with agents; these languages may embody principl...
A multi-agent system for enterprise integration
- Y Peng
Peng, Y. et al. (1998). A multi-agent system for enterprise integration. In Proceedings of the third international conference on the practical applications of agents and multi-agent systems (PAAM-98) (pp. 1–14).
Using ARCHON to develop real-word DAI applications, Part I
- Jennings
Jennings, N. R. et al. (1996). Using ARCHON to develop real-word DAI applications, Part I. IEEE Expert, 11(6), 64–70.
FIPA agent management specification, Foundation for Intelligent Physical Agents, http://www.fipa.org/specs
FIPA00023, 2000, FIPA agent management specification, Foundation for Intelligent Physical
Agents, http://www.fipa.org/specs/fipa00023/
Genesereth, M.R., Ketchpel, S.P., 1994, Communications of the ACM 37, 7.
Applications: Building the Knowledge Economy: Issues, Applications, Case Studies
- R Bañares-Alcántara
- P Ac Kokossis
- Linke
Bañares-Alcántara, R., AC Kokossis and P. Linke, 2003, Applications: Building the Knowledge
Economy: Issues, Applications, Case Studies, P. Cunningham, M. Cunningham, P. Fatelnig
(Editors), pp 892-897
Agent-based supply chain management - 1: Framework. Computers and Chemical Engineering
- Julka
Software agents: An overview. The Knowledge Engineering Review. v11 i3
- Nwana
Bioinformatics and multi-agent systems workshop {online}: <
- Bazzan Schroeder
- L F Schroeder
- A L C Bazzan
Multiagent systems. Artificial Intelligence Magazine. v19 i2
- Sycara
Intelligent agents: Theory and practice. The Knowledge Engineering Review. v10 i2
- Jennings Wooldridge
Ontology mapper: A multi-agent system for knowledge sharing. First UMBC mini-conference on multi-agent systems (MiCMAS’01)
- S Sansare
- U Shah
Towards a real-time multi-agent system architecture, {online}: <www.agentcities.org/Challenge02
- Soler
FIPA agent management specification, Foundation for Intelligent Physical Agents
- M R Ketchpel
FIPA00023, 2000, FIPA agent management specification, Foundation for Intelligent Physical
Agents, http://www.fipa.org/specs/fipa00023/
Genesereth, M.R., Ketchpel, S.P., 1994, Communications of the ACM 37, 7.
Knowledge Acquisition, 5. Nwana, H
- T R Gruber
Gruber, T. R., 1993, Knowledge Acquisition, 5.
Nwana, H., 1996, The Knowledge Engineering Review 11, 3.
Sycara, K. P., 1998, Artificial Intelligence Magazine 19, 2.
Bioinformatics and multi-agent systems workshop
- L F Schroeder
- A L C Bazzan